Cheaper Inference
Cheaper Inference
Model record / Alibaba
qwen3.6-plus is available for text generation from Alibaba. Its reported context window is 1,000,000 tokens, with up to 64,000 output tokens. Reported inputs: image, pdf, text. The served catalog lists image input, streaming.
Requests above 255,999 input tokens use $1.301143 input and $3.903429 output per 1M tokens.
Ready when you are
Marketplace pricing, capped at list, optimized further.
POST /v1/chat/completions
curl https://api.cheaperinference.com/v1/chat/completions \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "qwen3.6-plus", "messages": [ { "role": "user", "content": "Reply with the single word OK." } ], "max_tokens": 64 }'POST /v1/responses
curl https://api.cheaperinference.com/v1/responses \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": [ { "role": "user", "content": "Reply with the single word OK." } ], "model": "qwen3.6-plus", "store": false, "max_output_tokens": 256 }'POST /v1/messages
curl https://api.cheaperinference.com/v1/messages \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "qwen3.6-plus", "messages": [ { "role": "user", "content": "Reply with the single word OK." } ], "max_tokens": 1024 }'Capability source · checked
$0.813215 estimated at displayed rates
1,000,000 ÷ 1,000,000 × $0.325286 + 250,000 ÷ 1,000,000 × $1.951714
The same billed quantities at the listed reference rates: $1.25.
Uses uncached input at the displayed standard rates, with no extra modalities or tools. Billed output includes any charged reasoning tokens. Actual token counts, price tiers, and marketplace prices can change the total.
Price quote effective .
| Model | Current pricing | Context limit | Image input listed |
|---|---|---|---|
| qwen3.6-plus (this model)Alibaba | $0.325286 input / $1.951714 output per 1M tokens | 1,000,000 tokens | Yes |
| qwen3.5-plusAlibaba | $0.26 input / $1.56 output per 1M tokens | 1,000,000 tokens | Yes |
| qwen3.7-flashAlibaba | $0.0255 input / $0.1105 output per 1M tokens | 1,000,000 tokens | Yes |
| qwen3.7-plusAlibaba |
POST /v1/chat/completions
| Field | Values |
|---|---|
| reasoning.exclude | |
| max_tokens | |
| reasoning | effort: none, minimal, low, medium, high, xhigh, max; max_tokens: 1 to 131072 tokens; enabled: true or false |
| stop | |
| temperature | |
| tool_choice | |
| tools |
POST /v1/messages
| Field | Values |
|---|---|
| max_tokens | |
| thinking | type: enabled with budget_tokens (1 to 131072 tokens); output_config.effort: none, minimal, low, medium, high, xhigh, max |
| stop_sequences | |
| temperature | |
| tool_choice | |
| tools |
POST /v1/responses
| Field | Values |
|---|---|
| max_output_tokens | |
| reasoning | effort: none, minimal, low, medium, high, xhigh, max |
| temperature | |
| tool_choice | |
| tools |
See how much this model saves and when its recorded price has been lowest.
This model averaged 27.1% below comparable direct provider prices across the selected range. Its strongest observed window was 1:00 AM–10:00 AM in UTC.
Average saved
27.1%
Cheapest time
1:00 AM–10:00 AM
Hourly coverage
23/24
Signal quality
Growing
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#105
of 332 ranked models
Last 7 days
#159
of 389 ranked models
Last 30 days
#181
of 400 ranked models
| $0.264775 input / $1.0591 output per 1M tokens |
| 256,000 tokens |
| Yes |